diff --git a/content/chapters/02_dl_basics/02_01_optimization.md b/content/chapters/02_dl_basics/02_01_optimization.md
deleted file mode 100644
index db2760a..0000000
--- a/content/chapters/02_dl_basics/02_01_optimization.md
+++ /dev/null
@@ -1,13 +0,0 @@
----
-title: "Chapter 02.01: Optimization"
-weight: 2001
-
----
-This chapter discusses optimization and the optimization algorithm gradient descent. The variants of stochastic gradient descent are commonly used for deep learning.
-
-<!--more-->
-
-### Lecture slides
-
-{{< pdfjs file="https://github.com/slds-lmu/lecture_dl4nlp/blob/main/slides/chapter2-deeplearningbasics/slides-21-optimization.pdf" >}}
-
diff --git a/content/chapters/02_dl_basics/02_01_rnn.md b/content/chapters/02_dl_basics/02_01_rnn.md
new file mode 100644
index 0000000..76e9292
--- /dev/null
+++ b/content/chapters/02_dl_basics/02_01_rnn.md
@@ -0,0 +1,13 @@
+---
+title: "Chapter 02.01: Recurrent Neural Networks"
+weight: 2001
+
+---
+This chapter introduces Recurrent Neural Networks in the context of Language Modelling and discusses different types of RNNs, such as LSTMs and Bidirectional RNNs.
+
+<!--more-->
+
+### Lecture slides
+
+{{< pdfjs file="https://github.com/slds-lmu/lecture_dl4nlp/blob/main/slides/chapter02-deeplearningbasics/slides-21-rnn.pdf" >}}
+
diff --git a/content/chapters/02_dl_basics/02_02_attention.md b/content/chapters/02_dl_basics/02_02_attention.md
new file mode 100644
index 0000000..f9de821
--- /dev/null
+++ b/content/chapters/02_dl_basics/02_02_attention.md
@@ -0,0 +1,12 @@
+---
+title: "Chapter 02.02 Attention"
+weight: 2002
+---
+
+This chapter provides a first introduction to the Attention mechanism as a way to model long range dependencies.
+
+<!--more-->
+
+### Lecture slides
+
+{{< pdfjs file="https://github.com/slds-lmu/lecture_dl4nlp/blob/main/slides/chapter02-deeplearningbasics/slides-22-attention.pdf" >}}
\ No newline at end of file
diff --git a/content/chapters/02_dl_basics/02_02_dnns_activations.md b/content/chapters/02_dl_basics/02_02_dnns_activations.md
deleted file mode 100644
index 19d9761..0000000
--- a/content/chapters/02_dl_basics/02_02_dnns_activations.md
+++ /dev/null
@@ -1,12 +0,0 @@
----
-title: "Chapter 02.02 Deep Feedforward Networks"
-weight: 2002
----
-
-This chapter discusses Deep Forward Networks, the simplest type of neural networks and some common activation functions, also called non-linearities.
-
-<!--more-->
-
-### Lecture slides
-
-{{< pdfjs file="https://github.com/slds-lmu/lecture_dl4nlp/blob/main/slides/chapter2-deeplearningbasics/slides-22-dnns_activations.pdf" >}}
\ No newline at end of file
diff --git a/content/chapters/02_dl_basics/02_03_backpropagation.md b/content/chapters/02_dl_basics/02_03_backpropagation.md
deleted file mode 100644
index a7aeacd..0000000
--- a/content/chapters/02_dl_basics/02_03_backpropagation.md
+++ /dev/null
@@ -1,12 +0,0 @@
----
-title: "Chapter 02.03: Backpropagation"
-weight: 2003
----
-The ability to scale neural networks is a key criterion for the success of modern neural networks. The backpropagation algorithm powers the efficient computation of the gradients.
-
-<!--more-->
-
-### Lecture slides
-
-{{< pdfjs file="https://github.com/slds-lmu/lecture_dl4nlp/blob/main/slides/chapter2-deeplearningbasics/slides-23-backpropagation.pdf" >}}
-
diff --git a/content/chapters/02_dl_basics/02_03_elmo.md b/content/chapters/02_dl_basics/02_03_elmo.md
new file mode 100644
index 0000000..26797fb
--- /dev/null
+++ b/content/chapters/02_dl_basics/02_03_elmo.md
@@ -0,0 +1,12 @@
+---
+title: "Chapter 02.03: ELMo"
+weight: 2003
+---
+In this chapter we introduce ELMo, a modelling approach, that enables us to contextualize word embeddings.
+
+<!--more-->
+
+### Lecture slides
+
+{{< pdfjs file="https://github.com/slds-lmu/lecture_dl4nlp/blob/main/slides/chapter02-deeplearningbasics/slides-23-elmo.pdf" >}}
+
diff --git a/content/chapters/02_dl_basics/02_04_tokenization.md b/content/chapters/02_dl_basics/02_04_tokenization.md
new file mode 100644
index 0000000..69afea9
--- /dev/null
+++ b/content/chapters/02_dl_basics/02_04_tokenization.md
@@ -0,0 +1,11 @@
+---
+title: "Chapter 02.04 Revisiting words: Tokenization"
+weight: 2004
+---
+In order to feed text data into a model we have to tokenize it first. This chapter discusses various types of text tokenization.
+
+<!--more-->
+
+### Lecture slides
+
+{{< pdfjs file="https://github.com/slds-lmu/lecture_dl4nlp/blob/main/slides/chapter02-deeplearningbasics/slides-24-tokenization.pdf" >}}
diff --git a/content/chapters/02_dl_basics/02_regularization.md b/content/chapters/02_dl_basics/02_regularization.md
deleted file mode 100644
index bd13827..0000000
--- a/content/chapters/02_dl_basics/02_regularization.md
+++ /dev/null
@@ -1,11 +0,0 @@
----
-title: "Chapter 02.04 Regularization"
-weight: 2004
----
-Regularization provides the possibility to guide the learning process.
-
-<!--more-->
-
-### Lecture slides
-
-{{< pdfjs file="https://github.com/slds-lmu/lecture_dl4nlp/blob/main/slides/chapter2-deeplearningbasics/slides-24-regularization.pdf" >}}
diff --git a/content/chapters/02_dl_basics/_index.md b/content/chapters/02_dl_basics/_index.md
index a728fb7..b1e2479 100644
--- a/content/chapters/02_dl_basics/_index.md
+++ b/content/chapters/02_dl_basics/_index.md
@@ -1,10 +1,6 @@
 ---
 title: "Chapter 2: Deep Learning Basics"
 ---
-This chapter gives a quick introduction to the basic concepts of deep learning, such as optimization, simple Feedforward networks, backpropagation and regularization. A comprehensive introduction is given in [1].
+This chapter gives a quick introduction to the basic concepts of deep learning in the context of NLP, such as RNN, attention, ELMo and tokenization.
 
-<!--more-->
-
-### References 
-
-- [1] [Goodfellow et al., 2016](https://www.deeplearningbook.org/)
+<!--more-->
\ No newline at end of file